Oesophageal speech enhancement using poles stabilization and Kalman filtering

This paper presents an oesophageal speech enhancement algorithm. Such an exceptionally special type of voice is due to the laryngectomy undergone by those persons with larynx cancer. An oesophageal voice has extremely low intelligibility. This work proposes a method to improve its quality, which consists of stabilizing the transfer function poles of the vocal tract model so as to improve a signal´s fornants. With this aim, the joint use of two techniques has been applied: on the one hand, an algorithm that transforms the modulus and phase of vocal tract´s poles and, on the other hand, a Kalman filtering technique. When using this efficient speech enhancement procedure, the speech signal is usually modelled as an autoregressive (AR) process and represented in the state- space domain. The final speech improvement has been measured with the help of MDVP tools and the HNR parameter.